Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cyanheads/fema-mcp-server/agents-mdgit clone --depth 1 https://github.com/cyanheads/fema-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/cyanheads/fema-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/cyanheads/fema-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cyanheads/fema-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.05659 | $0.05659 |
| Opus 5 | $0.02830 | $0.02830 |
| Sonnet 5 | $0.01132 | $0.01132 |
| Haiku 4.5 | $0.00566 | $0.00566 |
Grade A, and why
fema-mcp-server AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
77% identical to obsidian-mcp-server AGENTS.md — 326 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Protocol
Server: fema-mcp-server
Version: 0.1.14
Framework: @cyanheads/mcp-ts-core ^0.12.3
Engines: Bun ≥1.3.0, Node ≥24.0.0
MCP SDK: @modelcontextprotocol/server ^2.0.0
Zod: ^4.4.3
Read the framework docs first:
node_modules/@cyanheads/mcp-ts-core/CLAUDE.mdcontains the full API reference — builders, Context, error codes, exports, patterns. This file covers server-specific conventions only.
Core Rules
- Logic throws, framework catches. Tool/resource handlers are pure — throw on failure, no
try/catch. PlainErroris fine; the framework catches, classifies, and formats. Use error factories (notFound(),validationError(), etc.) when the error code matters. - Use
ctx.logfor request-scoped logging. Noconsolecalls. - Use
ctx.statefor tenant-scoped storage. Never access persistence directly. - Need input the caller didn't supply?
return ctx.requestInput(...)and readctx.inputswhen the handler is re-entered. Neverawaitfor user input mid-handler. - Secrets in env vars only — never hardcoded.
- Close the loop on issues. When implementing work tracked by a GitHub issue, comment on the issue with what landed and close it. Do both — a comment without a close leaves stale issues open; a close without a comment leaves no record of what shipped. The comment is for future readers — state the concrete changes, not the conversation that produced them.
Patterns
Tool
import { tool, z } from '@cyanheads/mcp-ts-core';
export const femaSearchDisasters = tool('fema_search_disasters', {
description: 'Search federal disaster declarations by state, incident type, declaration type, and date range.',
annotations: { readOnlyHint: true, openWorldHint: true },
input: z.object({
state: z.string().length(2).optional().describe('Two-letter US state code (e.g. TX)'),
limit: z.number().int().default(20).describe('Max results (1–1000)'),
}),
output: z.object({
declarations: z.array(z.object({
disasterNumber: z.number().describe('Unique FEMA disaster number'),
declarationTitle: z.string().describe('Official disaster title'),
state: z.string().describe('Two-letter state code'),
})).describe('Matching disaster declarations'),
count: z.number().describe('Total matching records'),
}),
async handler(input, ctx) {
const results = await getOpenFemaService().searchDisasters(input, ctx);
ctx.log.info('Disaster search completed', { state: input.state, count: results.count });
return results;
},
format: (result) => [{
type: 'text',
text: result.declarations.map(d => `**${d.disasterNumber}**: ${d.declarationTitle} (${d.state})`).join('\n'),
}],
});
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 379 lines · 5,659 tokens per session scan A 54b069480b71
fema-mcp-server AGENTS.md is an instructions file published in the GitHub repository cyanheads/fema-mcp-server (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 5,659 tokens to every session, about $0.0283 per session on Opus 5. A static security scan graded it A with 0 findings. It is 77% identical to obsidian-mcp-server AGENTS.md, differing in 326 lines, and is treated as a copy.
Other instructions, from other repositories
gdelt-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/gdelt-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
orcid-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/orcid-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
ensembl-mcp-server CLAUDE.md
Instructions for cyanheads/ensembl-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
macos-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/macos-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
aviation-weather-mcp-server AGENTS.md
Instructions for cyanheads/aviation-weather-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
imf-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/imf-mcp-server, covering developer protocol, server overview, core rules, patterns and tool (with canvas spill).